1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
|
// Slurm regression test40.8.prog.cu
#include <iostream>
#include <math.h>
#include <sys/time.h>
// Kernel function to add the elements of two arrays
__global__
void add(int n, float *x, float *y)
{
int index = threadIdx.x;
int stride = blockDim.x;
for (int i = index; i < n; i += stride)
y[i] = x[i] + y[i];
}
int main(void)
{
int N = 1024 * 1024 * 16;
int i;
float *x, *y;
float maxError = 0.0f;
struct timeval tv1, tv2;
int delta_t;
// Get start time
gettimeofday(&tv1, NULL);
// Allocate Unified Memory – accessible from CPU or GPU
if (cudaMallocManaged(&x, N * sizeof(float)) != cudaSuccess) {
std::cerr << "Couldn't allocate memory for x: " << errno << std::endl;
return 1;
}
if (cudaMallocManaged(&y, N * sizeof(float)) != cudaSuccess) {
std::cerr << "Couldn't allocate memory for y: " << errno << std::endl;
return 1;
}
// initialize x and y arrays on the host
for (i = 0; i < N; i++) {
x[i] = 1.0f;
y[i] = 2.0f;
}
// Run kernel on 256 elements at a time on the GPU
add<<<1, 256>>>(N, x, y);
// Wait for GPU to finish before accessing on host
cudaDeviceSynchronize();
// Check for errors (all values should be 3.0f)
for (i = 0; i < N; i++)
maxError = fmax(maxError, fabs(y[i] - 3.0f));
std::cout << "Max error: " << maxError << std::endl;
// Free memory
cudaFree(x);
cudaFree(y);
// Get start time
gettimeofday(&tv2, NULL);
delta_t = (tv2.tv_sec - tv1.tv_sec) * 1000000;
delta_t += (tv2.tv_usec - tv1.tv_usec);
std::cout << "Run Time (usec): " << delta_t << std::endl;
return 0;
}
|
